ML-Net: multi-label classification of biomedical texts with deep neural networks (2018-11-13T00:00:00.000000Z)

Abstract

OBJECTIVE In multi-label text classification, each textual document is assigned 1 or more labels. As an important task that has broad applications in biomedicine, a number of different computational methods have been proposed. Many of these methods, however, have only modest accuracy or efficiency and limited success in practical use. We propose ML-Net, a novel end-to-end deep learning framework, for multi-label classification of biomedical texts. MATERIALS AND METHODS ML-Net combines a label prediction network with an automated label count prediction mechanism to provide an optimal set of labels. This is accomplished by leveraging both the predicted confidence score of each label and the deep contextual information (modeled by ELMo) in the target document. We evaluate ML-Net on 3 independent corpora in 2 text genres: biomedical literature and clinical notes. For evaluation, we use example-based measures, such as precision, recall, and the F measure. We also compare ML-Net with several competitive machine learning and deep learning baseline models. RESULTS Our benchmarking results show that ML-Net compares favorably to state-of-the-art methods in multi-label classification of biomedical text. ML-Net is also shown to be robust when evaluated on different text genres in biomedicine. CONCLUSION ML-Net is able to accuractely represent biomedical document context and dynamically estimate the label count in a more systematic and accurate manner. Unlike traditional machine learning methods, ML-Net does not require human effort for feature engineering and is a highly efficient and scalable approach to tasks with a large set of labels, so there is no need to build individual classifiers for each separate label.

Authors

References37 items

Automated ICD-9 Coding via A Deep Learning Approach

BioSentVec: creating sentence embeddings for biomedical texts

Extracting psychiatric stressors for suicide from social media using deep learning

Public Perception Analysis of Tweets During the 2015 Measles Outbreak: Comparative Study Using Convolutional Neural Network Models

TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-Rays

Using Social Media Data to Understand the Impact of Promotional Information on Laypeople’s Discussions: A Case Study of Lynch Syndrome

A histological ontology of the human cardiovascular system

Multi-Label Classification of Patient Notes a Case Study on ICD Code Assignment

Deep Learning for Extreme Multi-label Text Classification

Initializing neural networks for hierarchical multi-label text classification

MeSH Now: automatic MeSH indexing at PubMed scale via learning to rank

Improving Pairwise Ranking for Multi-label Image Classification

Text mining for improved exposure assessment

Hierarchical Attention Networks for Document Classification

DeepMeSH: deep semantic representation for improving large-scale MeSH indexing

MIMIC-III, a freely accessible critical care database

Automatic semantic classification of scientific literature according to the hallmarks of cancer

A Study of Neural Word Embeddings for Named Entity Recognition in Clinical Text

Adam: A Method for Stochastic Optimization

A Review on Multi-Label Learning Algorithms

Large-Scale Multi-label Text Classification - Revisiting Neural Networks

Diagnosis code assignment: models and evaluation metrics

Distributed Representations of Words and Phrases and their Compositionality

Recommending MeSH terms for annotating biomedical articles

Hallmarks of Cancer: The Next Generation

Adverse events in pregnant women following administration of trivalent inactivated influenza vaccine and live attenuated influenza vaccine in the Vaccine Adverse Event Reporting System, 1990-2009.

Rectified Linear Units Improve Restricted Boltzmann Machines

Classifier chains for multi-label classification

Learning multi-label scene classification

Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 2nd Edition

Deep Convolution Neural Network for Extreme Multi-label Text Classification

Combining rich features and deep learning for finding similar sentences in electronic medical records

Automated Classification of Multi-Labeled Patient Safety Reports: A Shift from Quantity to Quality Measure

Ensemble of Neural Networks for Multi-label Document Classification

Applying Deep Learning to ICD-9 Multi-label Classification from Medical Records

Distributional Semantics Resources for Biomedical Text Processing

Ieee Transactions on Knowledge and Data Engineering 1 Multi-label Neural Networks with Applications to Functional Genomics and Text Categorization